{
  "best_global_step": 1092,
  "best_metric": 0.9566188454020108,
  "best_model_checkpoint": "/kaggle/working/hpo_scibert_uncased/trial_6/checkpoint-1092",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 1092,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32051282051282054,
      "grad_norm": 121545.390625,
      "learning_rate": 4.628257110973899e-05,
      "loss": 0.6602,
      "step": 50
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 165566.34375,
      "learning_rate": 4.406384766248401e-05,
      "loss": 0.2825,
      "step": 100
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 183398.71875,
      "learning_rate": 4.184512421522902e-05,
      "loss": 0.2105,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_f1_macro": 0.9405513571748276,
      "eval_f1_micro": 0.9374337221633087,
      "eval_f1_weighted": 0.9373994117527249,
      "eval_loss": 0.19546222686767578,
      "eval_roc_auc_macro": 0.9773648844952434,
      "eval_runtime": 6.6101,
      "eval_samples_per_second": 54.008,
      "eval_steps_per_second": 0.908,
      "step": 156
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 119565.84375,
      "learning_rate": 3.962640076797404e-05,
      "loss": 0.1367,
      "step": 200
    },
    {
      "epoch": 1.6025641025641026,
      "grad_norm": 162723.625,
      "learning_rate": 3.740767732071905e-05,
      "loss": 0.1247,
      "step": 250
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 39087.80859375,
      "learning_rate": 3.5188953873464064e-05,
      "loss": 0.1182,
      "step": 300
    },
    {
      "epoch": 2.0,
      "eval_f1_macro": 0.9436427931387608,
      "eval_f1_micro": 0.94375,
      "eval_f1_weighted": 0.9438667437399432,
      "eval_loss": 0.16677653789520264,
      "eval_roc_auc_macro": 0.9820117282613596,
      "eval_runtime": 6.6121,
      "eval_samples_per_second": 53.992,
      "eval_steps_per_second": 0.907,
      "step": 312
    },
    {
      "epoch": 2.2435897435897436,
      "grad_norm": 125978.8359375,
      "learning_rate": 3.297023042620908e-05,
      "loss": 0.0894,
      "step": 350
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 264165.40625,
      "learning_rate": 3.0751506978954095e-05,
      "loss": 0.0687,
      "step": 400
    },
    {
      "epoch": 2.8846153846153846,
      "grad_norm": 68308.296875,
      "learning_rate": 2.853278353169911e-05,
      "loss": 0.0651,
      "step": 450
    },
    {
      "epoch": 3.0,
      "eval_f1_macro": 0.9445835024754138,
      "eval_f1_micro": 0.948024948024948,
      "eval_f1_weighted": 0.9482797012589066,
      "eval_loss": 0.15806053578853607,
      "eval_roc_auc_macro": 0.9879374351632613,
      "eval_runtime": 6.6786,
      "eval_samples_per_second": 53.454,
      "eval_steps_per_second": 0.898,
      "step": 468
    },
    {
      "epoch": 3.2051282051282053,
      "grad_norm": 15062.0087890625,
      "learning_rate": 2.6314060084444123e-05,
      "loss": 0.0452,
      "step": 500
    },
    {
      "epoch": 3.5256410256410255,
      "grad_norm": 10435.2138671875,
      "learning_rate": 2.409533663718914e-05,
      "loss": 0.0429,
      "step": 550
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 240173.984375,
      "learning_rate": 2.1876613189934154e-05,
      "loss": 0.0495,
      "step": 600
    },
    {
      "epoch": 4.0,
      "eval_f1_macro": 0.9468900491419501,
      "eval_f1_micro": 0.9495798319327731,
      "eval_f1_weighted": 0.9496287427368676,
      "eval_loss": 0.19388458132743835,
      "eval_roc_auc_macro": 0.9843316823250352,
      "eval_runtime": 6.5837,
      "eval_samples_per_second": 54.225,
      "eval_steps_per_second": 0.911,
      "step": 624
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 3220.84521484375,
      "learning_rate": 1.965788974267917e-05,
      "loss": 0.0278,
      "step": 650
    },
    {
      "epoch": 4.487179487179487,
      "grad_norm": 77989.6796875,
      "learning_rate": 1.7439166295424185e-05,
      "loss": 0.0328,
      "step": 700
    },
    {
      "epoch": 4.8076923076923075,
      "grad_norm": 17635.943359375,
      "learning_rate": 1.5220442848169199e-05,
      "loss": 0.0194,
      "step": 750
    },
    {
      "epoch": 5.0,
      "eval_f1_macro": 0.9542678396871944,
      "eval_f1_micro": 0.9544513457556936,
      "eval_f1_weighted": 0.954747368183765,
      "eval_loss": 0.17806702852249146,
      "eval_roc_auc_macro": 0.9850715189437066,
      "eval_runtime": 6.6153,
      "eval_samples_per_second": 53.966,
      "eval_steps_per_second": 0.907,
      "step": 780
    },
    {
      "epoch": 5.128205128205128,
      "grad_norm": 7326.7744140625,
      "learning_rate": 1.3001719400914214e-05,
      "loss": 0.0209,
      "step": 800
    },
    {
      "epoch": 5.448717948717949,
      "grad_norm": 42033.6640625,
      "learning_rate": 1.0782995953659228e-05,
      "loss": 0.0112,
      "step": 850
    },
    {
      "epoch": 5.769230769230769,
      "grad_norm": 20092.216796875,
      "learning_rate": 8.564272506404243e-06,
      "loss": 0.0179,
      "step": 900
    },
    {
      "epoch": 6.0,
      "eval_f1_macro": 0.9521823752294121,
      "eval_f1_micro": 0.955067920585162,
      "eval_f1_weighted": 0.9553084318062802,
      "eval_loss": 0.22233474254608154,
      "eval_roc_auc_macro": 0.9832222195348375,
      "eval_runtime": 6.606,
      "eval_samples_per_second": 54.042,
      "eval_steps_per_second": 0.908,
      "step": 936
    },
    {
      "epoch": 6.089743589743589,
      "grad_norm": 630.0228881835938,
      "learning_rate": 6.345549059149257e-06,
      "loss": 0.0115,
      "step": 950
    },
    {
      "epoch": 6.410256410256411,
      "grad_norm": 469.14447021484375,
      "learning_rate": 4.126825611894273e-06,
      "loss": 0.005,
      "step": 1000
    },
    {
      "epoch": 6.730769230769231,
      "grad_norm": 564.0679931640625,
      "learning_rate": 1.9081021646392873e-06,
      "loss": 0.0125,
      "step": 1050
    },
    {
      "epoch": 7.0,
      "eval_f1_macro": 0.9548856387728133,
      "eval_f1_micro": 0.9563409563409563,
      "eval_f1_weighted": 0.9566188454020108,
      "eval_loss": 0.2219453752040863,
      "eval_roc_auc_macro": 0.9854251710108592,
      "eval_runtime": 6.6485,
      "eval_samples_per_second": 53.697,
      "eval_steps_per_second": 0.902,
      "step": 1092
    }
  ],
  "logging_steps": 50,
  "max_steps": 1092,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9155639800000512.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}